INDEX

Explanations

lines of code related to defining or implementing functions and methods

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iger

-0.16

iqu

-0.15

loser

-0.14

Bes

-0.14

Gus

-0.14

ford

-0.14

.synthetic

-0.13

egas

-0.13

izedName

-0.13

POSITIVE LOGITS

0.15

otal

0.14

Ð¾ÑĤÑĮ

0.14

Ð³Ð¸

0.14

uisse

0.14

etooth

0.14

jÃŃm

0.13

faker

0.13

LIK

0.13

Activations Density 1.936%

lines of code related to defining or implementing functions and methods

No Comments

No Known Activations